Skip to main content
Glama

chronica_save_entry

Save important memories, decisions, tasks, and events to structured persistent memory for time-aware context across sessions.

Instructions

エントリ(記憶・記録)を保存します。

【使用タイミング】

  • ユーザーが新しい情報を提供したとき

  • 重要な決定事項があったとき

  • タスクや未決事項が発生したとき

  • 出来事や質問があったとき

【保存すべきタイミング】

  • 「覚えておいて」「忘れないで」「記録して」などの発言

  • 「今日〇〇をした」「〇〇に決めた」「〇〇をやる予定」

  • 新しい事実・決定・予定・気づき・感情が含まれる発言

  • 迷ったら保存する。保存しすぎるほうが保存漏れより良い。

  • 「保存しました」等の報告は不要。会話を自然に続ける。

【Claude向けの注意】

  • ユーザーに「保存しました」等の確認は不要

  • 自然に会話を続ける

  • メタ発言(「Chronicaに保存します」等)は避ける

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
entryYesEntry JSON(thread, kind, text, tags は必須)

Implementation Reference

  • The handler implementation for 'chronica_save_entry' in src/chronica/tools.py. It processes the input arguments, validates the structure, and calls the store.save_entry method.
    if name == "chronica_save_entry":
        entry = arguments.get("entry", {})
        
        # バリデーション
        if not entry:
            return [types.TextContent(
                type="text",
                text=json.dumps({"error": "internal_error", "message": "entry is required"}, ensure_ascii=False)
            )]
        
        # 必須フィールドのチェック
        if "kind" not in entry or not entry.get("kind"):
            return [types.TextContent(
                type="text",
                text=json.dumps({"error": "validation_error", "message": "entry.kind is required"}, ensure_ascii=False)
            )]
        
        if "text" not in entry or not entry.get("text"):
            return [types.TextContent(
                type="text",
                text=json.dumps({"error": "validation_error", "message": "entry.text is required"}, ensure_ascii=False)
            )]
        
        # threadの処理
        thread = entry.get("thread", {})
        if not isinstance(thread, dict):
            # threadが文字列の場合は、それをtypeとして使用
            if isinstance(thread, str):
                thread_type_str = thread
                thread = {"type": thread_type_str if thread_type_str in ["normal", "project"] else "normal"}
            else:
                thread = {"type": "normal"}
            entry["thread"] = thread
        
        thread_type = thread.get("type", "normal")
        if thread_type not in ["normal", "project"]:
            thread_type = "normal"
            thread["type"] = thread_type
        
        # tagsの処理(リストでない場合は空リストに)
        if "tags" not in entry:
            entry["tags"] = []
        elif not isinstance(entry["tags"], list):
            entry["tags"] = []
        
        if "event_time" in entry and isinstance(entry["event_time"], dict):
            event_time_raw = entry["event_time"].get("raw")
            if event_time_raw:
                anchor_time = entry.get("saved_time")
                parsed = parse_event_time(event_time_raw, anchor_time)
                entry["event_time"] = parsed
        
        try:
            entry_id = store.save_entry(entry)
            return [types.TextContent(
                type="text",
                text=json.dumps({"entry_id": entry_id}, ensure_ascii=False)
            )]
        except Exception as e:
            return [types.TextContent(
                type="text",
                text=json.dumps({"error": "save_error", "message": str(e)}, ensure_ascii=False)
            )]
  • The registration of 'chronica_save_entry' tool within the list_tools definition in src/chronica/tools.py.
                types.Tool(
                    name="chronica_save_entry",
                    description="""
    エントリ(記憶・記録)を保存します。
    
    【使用タイミング】
    - ユーザーが新しい情報を提供したとき
    - 重要な決定事項があったとき
    - タスクや未決事項が発生したとき
    - 出来事や質問があったとき
    
    【保存すべきタイミング】
    - 「覚えておいて」「忘れないで」「記録して」などの発言
    - 「今日〇〇をした」「〇〇に決めた」「〇〇をやる予定」
    - 新しい事実・決定・予定・気づき・感情が含まれる発言
    - 迷ったら保存する。保存しすぎるほうが保存漏れより良い。
    - 「保存しました」等の報告は不要。会話を自然に続ける。
    
    【Claude向けの注意】
    - ユーザーに「保存しました」等の確認は不要
    - 自然に会話を続ける
    - メタ発言(「Chronicaに保存します」等)は避ける
    """,
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "entry": {
                                "type": "object",
                                "description": "Entry JSON(thread, kind, text, tags は必須)"
                            }
                        },
                        "required": ["entry"]
                    }
                ),
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It successfully discloses UX behavioral traits: silent operation (no confirmation needed), natural conversation continuation, and the 'better to over-save' heuristic. However, it lacks technical behavioral details such as failure modes, persistence guarantees, or idempotency constraints that would be expected for a data mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Excellent structure with clear visual sections (【使用タイミング】, 【保存すべきタイミング】, 【Claude向けの注意】). Information is front-loaded with the purpose statement. Every bullet point provides specific, actionable triggers rather than generic advice. Length is appropriate for the complexity of the decision logic required.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (nested object parameter, specific UX contract) and lack of output schema, the description adequately covers the operational context. It explains what constitutes an entry, when to create one, and how to behave after invocation. Minor gap: does not mention return values or error handling behavior, though this is less critical given the silent-operation UX pattern described.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (the schema notes that thread, kind, text, and tags are required within the entry object). The description text itself adds no parameter syntax or semantic details beyond the schema. This meets the baseline expectation when schema coverage is high, but does not add supplementary context about the entry structure.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a clear, specific verb+resource statement: 'エントリ(記憶・記録)を保存します' (Save entries/memories/records). It clearly distinguishes this tool from siblings like `chronica_search` or `chronica_list_threads` by positioning it as the definitive write operation for persisting user information.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use guidance with specific trigger phrases ('覚えておいて', '今日〇〇をした') and scenarios (new information, decisions, tasks). Includes clear when-not-to-use guidance ('「保存しました」等の報告は不要') and explicit alternatives (avoid meta-comments, continue conversation naturally). This is exemplary usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Nic9dev/Chronica'

If you have feedback or need assistance with the MCP directory API, please join our Discord server